© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 9936
    Prev
    Next
    INDEX
    Explanations

    terms related to assessing various types of risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     laikā
    -0.52
     meille
    -0.42
     rígida
    -0.39
    enumi
    -0.39
     réguli
    -0.38
    encji
    -0.37
     stuffed
    -0.36
     darbu
    -0.36
     vandens
    -0.36
     moky
    -0.35
    POSITIVE LOGITS
     Risk
    1.13
     risk
    1.09
    Risk
    1.07
    risk
    1.00
     risks
    0.95
    RISK
    0.95
     RISK
    0.93
     Risks
    0.91
    risks
    0.82
    Risks
    0.81
    Activations Density 0.228%

    No Known Activations